Finding Paths through the World's Photos

Noah Snavely1         Rahul Garg1         Steven M. Seitz1         Richard Szeliski2
1University of Washington     2Microsoft Research    


When a scene is photographed many times by different people, the viewpoints often cluster along certain paths. These paths are largely specific to the scene being photographed, and traverse interesting regions and viewpoints. We seek to discover a range of such paths and turn them into controls for image-based rendering. Our approach takes as input a large set of community or personal photos, reconstructs camera viewpoints, and automatically computes orbits, panoramas, canonical views, and optimal paths between views. The scene can then be interactively browsed in 3D using these controls or with five degree-of-freedom free-viewpoint control. As the user browses the scene, nearby views are continuously selected and transformed, using control-adaptive reprojection techniques.

Code *New!*

Please visit the Bundler webpage to download code and binaries for our structure from motion system.

Noah Snavely, Rahul Garg, Steven M. Seitz, and Richard Szeliski.
Finding Paths through the World's Photos.
ACM Transactions on Graphics (SIGGRAPH 2008) [pdf]
  title   = {Finding Paths through the World's Photos},
  author  = {Noah Snavely and Rahul Garg and Steven M. Seitz and Richard Szeliski},
  year    = {2008},
  journal = {ACM Transactions on Graphics (Proceedings of SIGGRAPH 2008)},
  volume  = {27},
  number  = {3},
  pages   = {11-21}

Download an HQ version of the video in
[quicktime] or [wmv] format.

Watch the video on YouTube.


Special thanks to Kevin Chiu and Andy Hou for their help with this project. We also appreciate the many Flickr users who allowed us to use their photos.

Photo Tourism and Community Photo Collections

For more information on projects related to Photo Tourism, please visit the Photo Tourism project page.
Interested in Internet photo collections? Visit the Community Photo Collections page.